© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39866
    Prev
    Next
    INDEX
    Explanations

    F. Scott Fitzgerald

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    د
    0.74
    ل
    0.65
    Sep
    0.61
    ives
    0.61
    この
    0.60
    ۳
    0.59
     മൂ
    0.59
     वीडियोस
    0.59
    Xiaomi
    0.59
     ถึง
    0.58
    POSITIVE LOGITS
    s
    0.95
    y
    0.84
    t
    0.81
    ut
    0.75
    the
    0.71
    -
    0.68
    ar
    0.65
    ad
    0.64
    ের
    0.63
    en
    0.63
    Activations Density 0.000%

    No Known Activations